In [1]:

    

import pandas as pd
import datetime
import numpy as np
import scipy as sp
import os
import matplotlib.pyplot as plt
import matplotlib
%matplotlib inline
matplotlib.rcParams['figure.figsize'] = (12.0, 6.0)


    

In [2]:

    

raw = pd.read_csv("./market.csv", header=False, names=['time', 'price', 'volume'], index_col='time', parse_dates=[0])
raw.head()


    

    
Out[2]:






  

    

      

      
price
      
volume
    
    

      
time
      

      

    
  
  

    

      
2014-12-02
      
 377.00
      
 15.013600
    
    

      
2014-12-03
      
 377.90
      
  0.546608
    
    

      
2014-12-04
      
 377.10
      
  0.010000
    
    

      
2014-12-06
      
 378.00
      
  0.015000
    
    

      
2014-12-08
      
 375.01
      
  0.235000
    
  

In [3]:

    

data = raw['2015']
data.plot(secondary_y='volume', rot=0)


    

    
Out[3]:





<matplotlib.axes.AxesSubplot at 0x1075bf290>






    

In [4]:

    

data['shifted_vol'] = data['volume'].shift(1)
data.head()


    

    




-c:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy






    
Out[4]:






  

    

      

      
price
      
volume
      
shifted_vol
    
    

      
time
      

      

      

    
  
  

    

      
2015-01-08
      
 360.00
      
 10.350000
      
       NaN
    
    

      
2015-01-13
      
 260.00
      
  1.000000
      
 10.350000
    
    

      
2015-01-14
      
 200.00
      
 11.304638
      
  1.000000
    
    

      
2015-01-15
      
 191.99
      
  2.977321
      
 11.304638
    
    

      
2015-01-16
      
 210.98
      
  4.690000
      
  2.977321
    
  

In [6]:

    

data.iloc[:,[0,2]].plot(secondary_y='price', rot=0)


    

    
Out[6]:





<matplotlib.axes.AxesSubplot at 0x107b35bd0>






    

In [7]:

    

pct_data = raw['2015'].pct_change()
pct_data.head()


    

    
Out[7]:






  

    

      

      
price
      
volume
    
    

      
time
      

      

    
  
  

    

      
2015-01-08
      
      NaN
      
       NaN
    
    

      
2015-01-13
      
-0.277778
      
 -0.903382
    
    

      
2015-01-14
      
-0.230769
      
 10.304638
    
    

      
2015-01-15
      
-0.040050
      
 -0.736628
    
    

      
2015-01-16
      
 0.098911
      
  0.575242
    
  

In [8]:

    

pct_data.corr()


    

    
Out[8]:






  

    

      

      
price
      
volume
    
  
  

    

      
price
      
 1.000000
      
 0.314698
    
    

      
volume
      
 0.314698
      
 1.000000
    
  

In [9]:

    

pct_data.ix[pct_data['volume'].argmax()] = 0
pct_data.plot(secondary_y='volume', rot=0)


    

    
Out[9]:





<matplotlib.axes.AxesSubplot at 0x107b68350>






    

In [10]:

    

pct_data['shifted_volume'] = pct_data['volume'].shift(1)
pct_data.head()


    

    
Out[10]:






  

    

      

      
price
      
volume
      
shifted_volume
    
    

      
time
      

      

      

    
  
  

    

      
2015-01-08
      
      NaN
      
       NaN
      
       NaN
    
    

      
2015-01-13
      
-0.277778
      
 -0.903382
      
       NaN
    
    

      
2015-01-14
      
-0.230769
      
 10.304638
      
 -0.903382
    
    

      
2015-01-15
      
-0.040050
      
 -0.736628
      
 10.304638
    
    

      
2015-01-16
      
 0.098911
      
  0.575242
      
 -0.736628
    
  

In [11]:

    

pct_data.corr()


    

    
Out[11]:






  

    

      

      
price
      
volume
      
shifted_volume
    
  
  

    

      
price
      
 1.000000
      
 0.114096
      
-0.095263
    
    

      
volume
      
 0.114096
      
 1.000000
      
-0.054928
    
    

      
shifted_volume
      
-0.095263
      
-0.054928
      
 1.000000